US11064261B2 - Electronic device and control method therefor - Google Patents

Electronic device and control method therefor Download PDF

Info

Publication number
US11064261B2
US11064261B2 US16/638,354 US201816638354A US11064261B2 US 11064261 B2 US11064261 B2 US 11064261B2 US 201816638354 A US201816638354 A US 201816638354A US 11064261 B2 US11064261 B2 US 11064261B2
Authority
US
United States
Prior art keywords
content
electronic device
day
recommendation
specific event
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
US16/638,354
Other languages
English (en)
Other versions
US20200169789A1 (en
Inventor
Do-Sung Kim
Sung-Won Kim
Mu-gong BAE
Hyun-don YOON
Bong-Seok Lee
Hee-ran Lee
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Samsung Electronics Co Ltd
Original Assignee
Samsung Electronics Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Samsung Electronics Co Ltd filed Critical Samsung Electronics Co Ltd
Assigned to SAMSUNG ELECTRONICS CO., LTD. reassignment SAMSUNG ELECTRONICS CO., LTD. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: BAE, Mu-gong, KIM, DO-SUNG, KIM, SUNG-WON, LEE, BONG-SEOK, LEE, HEE-RAN, YOON, HYUN-DON
Publication of US20200169789A1 publication Critical patent/US20200169789A1/en
Application granted granted Critical
Publication of US11064261B2 publication Critical patent/US11064261B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/482—End-user interface for programme selection
    • H04N21/4826—End-user interface for programme selection using recommendation lists, e.g. of programmes or channels sorted out according to their score
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44213—Monitoring of end-user related data
    • H04N21/44222—Analytics of user selections, e.g. selection of programmes or purchase activity
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/4508—Management of client data or end-user data
    • H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/482—End-user interface for programme selection
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/845—Structuring of content, e.g. decomposing content into time segments
    • H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments

Definitions

  • the disclosure relates to an electronic device and a control method therefor, and more particularly, to an electronic device which can provide information on service recommendation on the basis of a device use history, and a control method therefor.
  • a user had to select a specific menu (e.g., a history service).
  • a specific menu e.g., a history service.
  • a history service was not used widely.
  • a user wanted to select a sport channel that he frequently viewed at a specific time, he chose the desired channel by searching the channel while keeping changing channels, or getting into the full program schedule, etc.
  • a user could set a channel that he frequently viewed as a bookmarked channel, or a reserved channel.
  • a plurality of setting operations were needed for this through a menu, and thus use frequency of this was not high.
  • the disclosure was devised for improving the aforementioned problem, and the purpose of the disclosure is in providing an electronic device which can provide information on service recommendation in case there is a specific action of a user on the basis of a device use history by utilizing minimum resources, and a control method therefor.
  • a method for recommending a content by an electronic device includes the steps of recommending a content on the basis of a viewing history, calculating recommendation hit ratios of the recommended content according to days of the week and times of the day on the basis of the selection frequency of the recommended content, and storing the same, and based on a specific event occurring, calculating a recommendation hit ratio of a content corresponding to the day and time when the specific event occurred, and based on the calculated recommendation hit ratio satisfying a predetermined condition, directly providing the content that satisfies the predetermined condition.
  • the predetermined condition means a case wherein the recommendation hit ratio is higher than a threshold value
  • the method for recommending a content by an electronic device may further include the step of, based on the recommendation hit ratio being lower than a threshold value, providing a menu which enables selection of a content corresponding to the day and time when the specific event occurred.
  • the method for recommending a content by an electronic device may further include the step of, based on cancellation of the menu being repeated greater than or equal to a threshold number of times, inactivating a content recommendation function.
  • the method for recommending a content by an electronic device may further include the step of, based on viewing of the content directly provided as the recommendation hit ratio is higher than a threshold value being cancelled greater than or equal to a threshold number of times, inactivating a content recommendation function.
  • the specific event may be an event wherein the number of times of changing broadcast channels during a predetermined time period exceeds a threshold number of times.
  • the specific event may be an event wherein a tuned state of a broadcast channel is maintained exceeding a predetermined time period.
  • the specific event may be an event wherein a viewing starting time or a viewing finishing time predicted on the basis of the viewing history comes.
  • the step of recommending a content on the basis of a viewing history may include the steps of applying a first weight to the day of viewing a content provided at the electronic device earlier, and applying a second weight to the time of viewing, and recommending a content based on a result of combination of the first weight and the second weight.
  • an electronic device includes a display, a memory storing a viewing history, and a processor configured to recommend a content on the basis of the viewing history, and calculate recommendation hit ratios of the recommended content according to days of the week and times of the day on the basis of the selection frequency of the recommended content, and store the same in the memory.
  • the processor based on a specific event occurring, calculates a recommendation hit ratio of a content corresponding to the day and time when the specific event occurred, and based on the calculated recommendation hit ratio satisfying a predetermined condition, directly provides the content that satisfies the predetermined condition.
  • the predetermined condition means a case wherein the recommendation hit ratio is higher than a threshold value
  • the processor may, based on the recommendation hit ratio being lower than a threshold value, control the display to provide a menu which enables selection of a content corresponding to the day and time when the specific event occurred.
  • the processor may, based on cancellation of the menu being repeated greater than or equal to a threshold number of times, inactivate a content recommendation function.
  • the processor may, based on viewing of the content directly provided as the recommendation hit ratio is higher than a threshold value being cancelled greater than or equal to a threshold number of times, inactivate a content recommendation function.
  • the specific event may be an event wherein the number of times of changing broadcast channels during a predetermined time period exceeds a threshold number of times.
  • the specific event may be an event wherein a tuned state of a broadcast channel is maintained exceeding a predetermined time period.
  • the specific event may be an event wherein a viewing starting time or a viewing finishing time predicted on the basis of the viewing history comes.
  • the processor may apply a first weight to the day of viewing a content provided at the electronic device earlier, and apply a second weight to the time of viewing, and recommend a content based on a result of combination of the first weight and the second weight.
  • the processor may count cases wherein a user actually views the recommended content, and store a ratio between counted contents as a hit ratio in a memory.
  • the recommendation method includes the steps of recommending a content on the basis of a viewing history, calculating recommendation hit ratios of the recommended content according to days of the week and times of the day on the basis of the selection frequency of the recommended content, and storing the same, and based on a specific event occurring, calculating a recommendation hit ratio of a content corresponding to the day and time when the specific event occurred, and based on the calculated recommendation hit ratio satisfying a predetermined condition, directly providing the content that satisfies the predetermined condition.
  • FIG. 1 is a block diagram for illustrating a configuration of an electronic device according to an embodiment of the disclosure
  • FIG. 2 is a block diagram for illustrating a configuration of an electronic device according to another embodiment of the disclosure.
  • FIG. 3 is a diagram for illustrating a method for providing a recommended content according to an embodiment of the disclosure
  • FIG. 4 is a diagram for illustrating a method for providing a recommended content according to an embodiment of the disclosure
  • FIG. 5 is a diagram for illustrating various embodiments of the disclosure of selecting a recommended content based on history information
  • FIG. 6 is a diagram for illustrating a method for calculating a recommendation hit ratio based on a recommended content
  • FIG. 7 is a flow chart for illustrating a method for recommending a content according to an embodiment of the disclosure.
  • FIG. 8 is a flow chart for illustrating a method for recommending a content according to an embodiment of the disclosure
  • FIG. 9 is a flow chart for illustrating a method for recommending a content according to an embodiment of the disclosure.
  • FIG. 10 is a flow chart for illustrating a method for recommending a content according to another embodiment of the disclosure.
  • FIG. 11 is a flow chart for illustrating a method for recommending a content by an electronic device according to an embodiment of the disclosure.
  • ordinal numbers such as “the first” and “the second” may be used for distinguishing components. Such ordinal numbers are used for distinguishing the same or similar components from one another, and it is not intended that the meaning of terms is restrictively interpreted due to use of such ordinal numbers. As an example, the order of use or the order of arrangement, etc. of a component combined with such ordinal numbers should not be restricted by the numbers. Depending on needs, each ordinal number may be used while being replaced with each other.
  • a module a unit and “a part” are for referring to elements performing at least one function or operation, and these elements may be implemented as hardware or software, or as a combination of hardware and software. Further, a plurality of “modules,” “units,” “parts” and the like may be integrated into at least one module or chip and implemented as at least one processor, except when each of them has to be implemented as individual, specific hardware.
  • the description that a part is connected with another part not only includes a case of direct connection, but also includes a case of indirect connection through another medium.
  • the description that a part includes an element means that another element may be further included, but not that another element is excluded, unless there is a particular opposing description.
  • the meaning of recommending a content may include the step of selecting a content on the basis of a viewing history stored in a memory and calculating history information and recommendation hit ratios in this regard. Also, it may mean converting to a content directly or displaying a menu inquiring whether to perform conversion. In this case, the meaning of ‘specific,’ threshold,′ or ‘any’ may mean a predetermined value.
  • FIG. 1 is a block diagram for illustrating a configuration of an electronic device according to an embodiment of the disclosure.
  • the electronic device 100 may include a memory 110 , a processor 120 , and a display 131 .
  • the electronic device 100 may be implemented as various devices such as a computer, a TV, a set-top box, a smartphone, and a smart watch.
  • the electronic device 100 may be implemented as an analog TV, a digital TV, a 3D-TV, a smart TV, an LED TV, an OLED TV, a plasma TV, a monitor, a curved TV having a screen of a fixed curvature, a flexible TV having a screen of a fixed curvature, a bended TV having a screen of a fixed curvature, and/or a curvature variable TV wherein the curvature of the current screen can be changed by a received user input, etc., but is not limited thereto.
  • the electronic device 100 may receive input of a voice through an internal microphone 150 or a microphone installed inside an external device and perform voice recognition directly, or transmit an input voice to an external server performing voice recognition and receive a result of voice recognition.
  • an artificial intelligence system for recognizing voices may be provided on it.
  • An artificial intelligence system is a computer system implementing intelligence of a human level and is a system wherein a machine learns and determines by itself, and which shows a more improved recognition rate as it is used more.
  • An artificial intelligence system may recognize an input voice through a linguistic understanding technology of recognizing human languages/characters among artificial intelligence technologies. Linguistic understanding is a technology of recognizing human languages/characters, and applying/processing them, and includes natural speech processing, machine translation, communication systems, queries and answers, voice recognition/synthesis, and the like.
  • a separate external device having a microphone stored therein exists, and the external device may perform a voice recognition process for an input voice and provide a result of voice recognition to the electronic device 100 .
  • the electronic device 100 may be controlled based on the result of voice recognition. For example, if the result of voice recognition includes “Recommend me a channel,” the electronic device 100 may select a recommended channel and provide information on the selected recommended channel through an outputter 130 .
  • the memory 110 stores information on the use history of the electronic device 100 .
  • Main information stored includes the ON/OFF time of the electronic device 100 , the viewing history (channels, titles, additional information of programs, etc.), the execution history of apps, the input history such as input of a remote control and input of a voice, the use history of functions (a menu, etc.), and the like, and information on the time points of use is also stored.
  • the information stored may be deleted after a specific time period passes.
  • weights W 1 , W 2 , W 3 to be added to a history are stored.
  • a use pattern that continuously changes is reflected, and the weight may be periodically updated.
  • a task of checking in this regard periodically may be repeated. Specifically, when a periodic update schedule comes, the processor 120 may perform a query to the server 200 and update a weight.
  • the memory 110 may store various kinds of application programs, data, and software modules for operating and controlling the electronic device 100 by control of the processor 120 .
  • the memory 110 may include a history storing/analyzing module storing a use history of a service provided by the electronic device 100 , a curator module selecting a recommended service, a service exposing module providing information on the selected recommended service, a voice recognition module, an image recognition module, etc.
  • the memory 110 information on a history that a user used the electronic device 100 may be stored.
  • the history information may include, for example, the device ON/OFF time of the electronic device 100 , the use history of contents, input information (a remote control, a voice, etc.), a use history of functions (a history of selecting a menu, etc.), and the like.
  • the memory 110 may store history information according to days of the week and times of the day for each of the at least one content provided at the electronic device 100 .
  • the memory 110 may store only history information according to days, or store only history information according to times.
  • history information may include information on when (the date and the time) a specific content was used, and how long (the time of use) the content was used. To the history information, a new history may be added as a user uses a content, and the history information may be updated.
  • a content may be, for example, a broadcast channel, a broadcast content (e.g., a VoD, a streaming content (an image, music, etc.)), or a plurality of applications, functions, etc. that can be executed at the electronic device 100 .
  • history information may include, for example, information on when a specific broadcast channel was viewed, and how long the channel was viewed, and may include information on when a specific application was used, and how long the application was used, and may include information on when a specific content was reproduced, and how long the content was reproduced.
  • the disclosure is not limited to the aforementioned embodiment, and various history information may be stored in the memory 110 according to which content the electronic device 100 provides.
  • the memory 110 may be implemented as a non-volatile memory, a volatile memory, a flash-memory, a hard disk drive (HDD), or a solid state drive (SSD), etc. Meanwhile, the memory 110 may be implemented not only as a storage medium inside the electronic device 100 , but also as an external storage medium, e.g., a micro SD card, a USB memory, or a Web server through a network, etc.
  • the processor 120 controls the overall operations of the electronic device 100 .
  • the processor 120 may recommend a content on the basis of a viewing history, and calculate recommendation hit ratios of the recommended content according to days of the week and times of the day on the basis of the selection frequency of the recommended content, and store the same in the memory 110 .
  • the operation of recommending a content means an operation of searching a content corresponding to the day and time like selecting a content and determining a content appropriate for a user, and may be used as a meaning of selecting a content. Meanwhile, a method for calculating a recommendation hit ratio will be described later with reference to FIG. 9 .
  • the processor 120 may calculate a recommendation hit ratio of a content corresponding to the day and time when the specific event occurred, and if the calculated recommendation hit ratio satisfies a predetermined condition, the processor 120 may directly provide the content that satisfies the predetermined condition.
  • the predetermined condition means a case wherein the recommendation hit ratio is higher than a threshold value, and if the recommendation hit ratio is lower than a threshold value, the processor 120 may control the display 131 to provide a menu which enables selection of a content corresponding to the day and time when the specific event occurred.
  • the processor 120 may control the display 131 to directly display a content of which recommendation hit ratio is the maximum among a plurality of contents of which recommendation hit ratios are higher than a threshold value, and if the recommendation hit ratio of a content corresponding to the day and time when the event occurred is lower than a threshold value, the processor 120 may control the display 131 to display a plurality of recommended contents when the event occurred, and display a menu which enables selection of one among the plurality of contents.
  • the processor 120 may provide information on a content that a user is highly likely to use at the time point when the event occurs based on history information stored in the memory 110 to the user. Also, the processor 120 may provide recommendation information for the content by using an artificial intelligence technology.
  • An artificial intelligence technology consists of a machine learning (deep learning) technology using an algorithm which classifies/learns the characteristics of input data by itself, and element technologies of simulating functions of a human brain such as cognition and determination by using a machine learning algorithm.
  • Recommendation information for a content may be provided by using an inference/prediction technology of determining information and making logical inference and prediction among artificial intelligence technologies. Inference/prediction is a technology of determining information and making logical inference and prediction, and may include knowledge/probability based inference, optimization prediction, preference based planning, recommendation, and the like.
  • the processor 120 may add a weight to a history corresponding to at least one of the day or time when the event occurred, and select a recommended content among a plurality of contents based on the history that the weight was added.
  • a history indicates at least one of the number of times of using contents included in the history information or the time of using the contents.
  • a specific event may be one of an event wherein the number of times of changing broadcast channels during a predetermined time period exceeds a threshold number of times, an event wherein a tuned state of a broadcast channel is maintained exceeding a predetermined time period, or an event wherein a predicted viewing starting time or viewing finishing time comes on the basis of the viewing history.
  • a specific event may be, for example, an event wherein a user selects a specific button of a remote control device controlling the electronic device 100 , and a control signal corresponding thereto is received at the electronic device 100 .
  • the electronic device 100 may receive a voice command
  • a specific event may be an event wherein a user utters a specific voice, for example, “Recommend me a channel,” and the voice command is received at the electronic device 100 .
  • a specific event may be an event wherein the electronic device 100 is turned on.
  • a specific event may be an event wherein a recommendation menu displayed on the touch screen of the electronic device 100 is selected.
  • a specific event may be an event wherein a predetermined time comes.
  • a specific event may be an event wherein history information stored in the memory 110 is updated.
  • the disclosure is not limited to the aforementioned examples, and any case wherein recommendation of a content is required may be set as a specific event.
  • the processor 120 may add a first weight W 1 to a history corresponding to the time when the specific event occurred, and add a second weight W 2 to a history corresponding to the day when the specific event occurred, and add a third weight W 3 to a history corresponding to a day and a time different from the day and the time when the specific event occurred, and calculate use indices for each of a plurality of contents. Then, the processor 120 may select a recommended content based on the order of having higher use indices.
  • the first weight, the second weight, and the third weight may be values different from one another, and the sizes of the values may be bigger in the order of the first weight, the second weight, and the third weight.
  • the third weight may be set as “1” which is a default value.
  • respective weights may be added to all of a history corresponding to the time when the specific event occurred, a history corresponding to the day when the specific event occurred, and a history corresponding to a day and a time different from the day and the time when the specific event occurred.
  • weights are added to only one or two of the three, and use indices are calculated.
  • the processor 120 may apply the first weight to the day of viewing a content provided at the electronic device earlier, and apply the second weight to the viewing time, and recommend a content based on a result of combination of the first weight and the second weight. Also, the processor 120 may count cases wherein a user actually views the recommended content, and store a ratio between counted contents as a hit ratio in the memory 110 .
  • the processor 120 may count the number of times that a user cancels a recommendation function, and determine whether the number of times is greater than a threshold number of times. Specifically, if cancellation of a menu is repeated greater than or equal to a threshold number of times, the processor 120 may inactivate a content recommendation function, and if a recommendation hit ratio is higher than a threshold value and viewing of a content directly provided is cancelled greater than or equal to a threshold number of times, the processor 120 may inactivate a content recommendation function.
  • the aforementioned function falls under an operation of reflecting a habit of not using a content even though the processor 120 provides a content automatically recommended. If a user showed an operation of not using a recommendation function greater than or equal to a threshold number of times and cancelling the function directly, the processor 120 may reflect this and may not provide a recommendation function anymore.
  • the cancelling operation may be a user's behavior of changing to the original channel again even though the processor 120 performed an operation of converting (moving) to a recommended content directly.
  • the cancelling operation may mean an operation wherein, even though a menu for a recommended content is displayed, a user clicks a close or cancellation button and does not use a content recommendation function.
  • the processor 120 may not provide a recommendation function at a specific time or on a specific day, and may automatically change the setting so that a recommendation function is not provided anymore.
  • the processor 120 may recognize an image displayed on the display 131 and determine a service currently used, and generate history information based on the determination result.
  • an artificial intelligence system for image recognition may be provided.
  • An artificial intelligence system is a computer system implementing intelligence of a human level and is a system wherein a machine learns and determines by itself, and which shows a more improved recognition rate as it is used more.
  • An image may be recognized through a visual understanding technology of recognizing an object in a similar manner to human vision among artificial intelligence technologies.
  • Visual understanding is a technology of recognizing an object in a similar manner to human vision, and processing the object, and includes recognition of an object, tracking of an object, search of an image, recognition of humans, understanding of a scene, understanding of a space, improvement of an image, and the like.
  • the processor 120 performs an operation of controlling the overall operations of the electronic device 100 and flow of signals among internal components of the electronic device 100 , and processing data.
  • the processor 120 includes a RAM 121 , a ROM 122 , a CPU 123 , and a bus 124 .
  • the RAM 121 , the ROM 122 , and the CPU 123 may be connected with one another through the bus 124 .
  • the processor 120 may be implemented as a system on chip (SoC).
  • SoC system on chip
  • the CPU 123 accesses the memory 110 , and performs booting by using an O/S stored in the memory 110 . Then, the CPU 123 performs various operations by using various kinds of programs, contents, data, etc. stored in the memory 110 . Also, the CPU 123 may perform the operation of the processor 120 explained with reference to FIG. 1 .
  • the GPU 124 may generate a screen including various objects such as icons, images, and texts.
  • a GPU may be constituted as a separate component such as an image processor 160 , and may be implemented as a component such as an SoC combined with a CPU inside the processor 120 .
  • the ROM 122 stores a set of instructions for system booting, etc.
  • the CPU 123 copies the O/S stored in the memory 110 in the RAM 121 according to the instruction stored in the ROM 122 , and boots the system by executing the O/S.
  • the CPU 123 copies various kinds of application programs stored in the memory 110 in the RAM 121 , and performs various operations by executing the application programs copied in the RAM 121 .
  • the processor 120 may perform various operations by using a module stored in the memory 110 .
  • the display 131 may display an image such that a user can see a recommended content provided by the processor 120 . Also, the display 131 may additionally display a UI element to a user while displaying an image.
  • the UI element may be a phrase requesting selection to the user, or a menu displaying a plurality of recommended contents.
  • the UI element may be an interface that can be recognized separately from contents, without being limited to a specific content.
  • the display 131 may be implemented as a liquid crystal display (LCD), a plasma display panel (PDP), organic light emitting diodes (OLEDs), etc., and it may also be implemented as a touch screen.
  • LCD liquid crystal display
  • PDP plasma display panel
  • OLEDs organic light emitting diodes
  • the electronic device 100 may calculate a history index by adding a weight according to a day and a time in a viewing history or may additionally calculate a recommendation hit ratio. Determination according to a day and a time is based on the feature that a user's content consumption pattern is repeated by a unit of a week, and this may be one month or one day, but not one week, according to a user's habit. If different weights are added according to days and times, a content that a user consumes on a specific day at a specific time can be analyzed precisely, and weights may be adjusted appropriately for a user.
  • a content can be recommended mainly based on contents that a user recently consumed, and thus a user's changing consumption pattern can be reflected.
  • the electronic device 100 may identify whether a recommended content is appropriate for a user, and may change values that a user can set in advance such as a weight and a threshold value by reflecting this. Through the operation of changing a weight, a threshold value, etc., a content that is more appropriate for a user can be recommended.
  • the electronic device 100 may analyze a user's pattern that did not use a recommendation function. By reflecting a user's intention by counting the number of times of not using a recommendation function, a consumer's satisfaction can be heightened.
  • processor 120 performs an operation of converting (displaying) a content directly under a specific condition, etc., a user can access a content that he wishes to view easily, without a separate access to a menu.
  • the electronic device 100 may additionally include components as illustrated in FIG. 2 . Detailed description of the components of the electronic device 100 will be made below with reference to FIG. 2 .
  • FIG. 2 is a block diagram for illustrating the configuration of the electronic device 100 according to another embodiment of the disclosure.
  • the electronic device 100 may include a memory 110 , a processor 120 , an outputter 130 , a display 131 , a communicator 140 , a tuner 150 , a microphone 160 , and a port part 170 .
  • the outputter 130 may include a display 131 for outputting images, and a speaker 132 for outputting audio.
  • the speaker 132 is a component outputting audio.
  • the speaker 132 is an acoustic device that changes an electronic signal into vibration of a vibration plate and generates a dilatational wave in the air, and thereby copies a sound wave, and it may output voice data.
  • the communicator 140 is a component performing communication with various types of external devices according to various types of communication methods.
  • the communicator 140 may be connected to an external device through a local area network (LAN) or an Internet network, or it may be connected with an external device by a wireless communication method (e.g., wireless communication such as Z-wave, 4LoWPAN, RFID, LTE D2D, BLE, GPRS, Weightless, Edge Zigbee, ANT+, NFC, IrDA, DECT, WLAN, Bluetooth, Wi-Fi, Wi-Fi Direct, GSM, UMTS, LTE, WiBRO, and the like).
  • a wireless communication method e.g., wireless communication such as Z-wave, 4LoWPAN, RFID, LTE D2D, BLE, GPRS, Weightless, Edge Zigbee, ANT+, NFC, IrDA, DECT, WLAN, Bluetooth, Wi-Fi, Wi-Fi Direct, GSM, UMTS, LTE, WiBRO, and the like
  • the communicator 140 may include various communication chips such as a Wi-Fi chip, a Bluetooth chip, an NFC chip, a wireless communication chip, and the like.
  • a Wi-Fi chip, a Bluetooth chip, and an NFC chip respectively perform communication by a Wi-Fi method, a Bluetooth method, and an NFC method.
  • a wireless communication chip means a chip that performs communication according to various communication standards such as IEEE, Zigbee, 3rd Generation (3G), 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), and the like.
  • the communicator 140 may include a light receiver that can receive a control signal (e.g., an IR pulse) from an external device.
  • a control signal e.g., an IR pulse
  • a user command input from an external device may be received, and information on a selected recommended service may be transmitted to an external user terminal through the communicator 140 , and data may be transmitted and received with a server 200 through the communicator 140 .
  • the tuner 150 may receive video, audio, and data in a frequency band corresponding to a channel number corresponding to a user input.
  • the tuner 150 may receive broadcast signals from various sources such as ground wave broadcasting, cable broadcasting, or satellite broadcasting. Also, the tuner 150 may receive broadcast signals from sources such as analog broadcasting or digital broadcasting among various sources.
  • the tuner 150 may be implemented as an all-in-one type with the electronic device 100 or as a separate device having a tuner unit that is electronically connected with the electronic device 100 (e.g., a set-top box, a tuner connected to the port part 170 ).
  • the tuner 150 may tune only the frequency of the channel to be received at the electronic device 100 among numerous electric wave components through amplification, mixing, resonance, etc. of a broadcast signal received by wire or wirelessly, and select the frequency.
  • a broadcast signal may include video, audio, and additional data (e.g., an electronic program guide (EPG)).
  • EPG electronic program guide
  • the port part 170 is a component for being connected with an external device.
  • the port part 170 may include at least one of a high-definition multimedia interface (HDMI) input port 171 , a component input jack 172 , or a USB port 173 .
  • the port part 170 may include at least one of ports such as an RGB, a DVI, an HDMI, a DP, and a thunderbolt. It is possible that information on a recommended service is transmitted to an external device through the port part 170 .
  • HDMI high-definition multimedia interface
  • FIGS. 3 and 4 are diagrams for illustrating a method for providing a recommended content according to an embodiment of the disclosure.
  • FIG. 3 is a diagram for illustrating that a screen displayed on the display 131 varies according to a recommendation hit ratio.
  • the processor 120 may recommend a content.
  • the processor 120 may display a menu selecting a recommended content within a range of not interfering with the currently displayed content 350 .
  • the part wherein the menu is displayed may be a specific edge or lower end of the display 131 .
  • the location may be another specific location.
  • at least one content of the channel number or the channel name may be displayed, or the types of programs currently broadcasted such as dramas, sports, entertainment, and the like may be added and displayed. If there are a plurality of recommended contents, the contents may be displayed in the order of top to bottom according to recommendation hit ratios or use indices. Afterwards, if a user selects a specific channel 360 , the processor 120 may convert to the selected content 370 .
  • FIG. 4 is a diagram displaying a UI inquiring to a user whether to view a specific content on the display 131 .
  • the processor 120 may display a screen which enables selection for a user regarding what type of content the user will watch, without specifying a channel. For example, in case there is a history of viewing a content by using a replay function such as a smart TV and an IPTV, but not a program that is currently viewed in a general case, there are few cases wherein a user watches the same content. Accordingly, the processor 120 may display a screen which recommends a similar type of recommended content instead of recommending the same content, and enables movement to a menu wherein contents of the type are collected.
  • a content previously viewed consists of a plurality of episodes, the next episode of the content may be recommended.
  • the processor 120 may display a UI element inquiring to the user whether to watch a movie after a specific event occurred 410. If the user wants to watch a movie, the user may click a button, and the processor 120 may display a menu which enables selection of a movie.
  • FIG. 5 is a diagram for illustrating various embodiments of the disclosure of selecting a recommended content based on history information.
  • a plurality of contents are broadcast channels, and there is a channel viewing history of from 2017 Jul. 24 to 2017 Jul. 30 in the memory 110 .
  • a specific event e.g., a user selects a specific button of a remote control
  • a first weight W 1 is added to a viewing history corresponding to the times to which 20 o'clock belongs, and a second weight W 2 is added to a viewing history corresponding to Saturday, and a third weight W 3 is added to a viewing history corresponding to the other days and time zones, and use indices of each of the plurality of broadcast channels are calculated.
  • the use index for the CB # channel is 4 ⁇ W 3 .
  • the use index for the FO # channel is 1 ⁇ W 1 +1 ⁇ W 2 .
  • the use index for the ESP # channel is 3 ⁇ W 1 +1 ⁇ W 3 .
  • the use index for the TN # channel is 2 ⁇ W 1 .
  • the use index for the Golf channel is 1 ⁇ W 3 .
  • a use index is calculated based on the number of times of use (the number of times of viewing).
  • a use index may be calculated based on the time of use (the time of viewing). The time of use may be calculated while being divided by a unit of one hour.
  • the use index for the CB # channel is 1 hr ⁇ W 3 +1 hr ⁇ W 3 +1 hr ⁇ W 3 +1 hr ⁇ W 3 +1 hr ⁇ W 3 .
  • the use index for the FO # channel is 1 hr ⁇ W 2 +1 hr ⁇ (W 1 +W 2 ).
  • the use index for the TN # channel is 1 hr ⁇ W 3 +1 hr ⁇ W 1 +1 hr ⁇ W 3 +1 hr ⁇ W 1 .
  • the use index for the Golf channel is 1 hr ⁇ W 3 +1 hr ⁇ W 3 . Summing up the above, it is as shown in Table 1 below.
  • a use index is calculated with one hour as one unit.
  • a use index may be calculated with the time period from a viewing starting time to a viewing finishing time of a specific channel as one unit.
  • the use index for the CB # channel is 1 hr ⁇ W 3 +1 hr ⁇ W 3 +1 hr ⁇ W 3 +1 hr ⁇ W 3 +1 hr ⁇ W 3 .
  • the use index for the FO # channel is 2 hr ⁇ (W 1 +W 2 ).
  • the use index for the ESP # channel is 3 hr ⁇ W 1 +2 hr ⁇ W 1 +2 hr ⁇ W 1 +2 hr ⁇ W 3 .
  • the use index for the TN # channel is 2 hr ⁇ W 1 +2 hr ⁇ W 1 .
  • the use index for the Golf channel is 2 hr ⁇ W 3 . Summing up the above, it is as shown in Table 2 below.
  • a use index may be calculated by applying a reduction value corresponding to the date when a content corresponding to a history was performed. That is, in the aforementioned embodiments, it was explained that a use index was calculated based on ‘a use time T ⁇ a weight W,’ but according to an embodiment wherein a reduction value is applied, a use index is calculated based on ‘a reduction value R ⁇ a use time T ⁇ a weight W.’
  • a reduction value may be set such that a reduction ratio becomes bigger as a date is earlier.
  • a reduction value A may be defined as follows.
  • a reduction value R (1 ⁇ r) ⁇ circumflex over ( ) ⁇ d.
  • 0 ⁇ r ⁇ 1 0 ⁇ r ⁇ 1
  • d 0 ⁇ r ⁇ 1
  • d d is a difference between a date when a content corresponding to a history was performed and a date when an event occurred.
  • the use index is calculated as (1 ⁇ r) ⁇ circumflex over ( ) ⁇ 9 ⁇ 1 hr ⁇ W 3 , and regarding viewing of CB # from 22 to 23 of 2017 Jul. 28, the use index is calculated as (1 ⁇ r) ⁇ circumflex over ( ) ⁇ 8 ⁇ 1 hr ⁇ W 3 .
  • Table 3 When calculation is also made for other channels in the same manner, it is as shown in Table 3 below.
  • the processor 120 may select the ESP # channel of which use index is the highest as a recommended content, or select the ESP # channel, the TN # channel, and the FO # channel which are within a predetermined rank (e.g., the third rank) as recommended contents.
  • a predetermined rank e.g., the third rank
  • the processor 120 may provide information on a selected recommended content through the outputter 130 .
  • the outtputer 130 is a component that can provide information on a recommended content, and for example, it may be implemented as a speaker 132 or a display 131 provided on the electronic device 100 .
  • a UI element which enables selection of at least one channel selected as a recommended channel may be displayed.
  • a user may select a desired channel through the UI element and view the channel.
  • the contents may be provided while being aligned in the order of having a bigger use index.
  • an indicator e.g., indication in the form of a star
  • an indicator may be displayed on a part wherein a recommended broadcast channel is located on the UI in the form of a scroll.
  • the processor 120 of the electronic device 100 may provide a UI in the form of a scroll.
  • a UI in the form of a scroll a plurality of channels are mapped, and a channel may be selected by moving the cursor up and down through a remote control device. Specifically, if the cursor moves and stays on a specific location for a specific time period, a channel corresponding to the location may be selected.
  • an indicator informing the locations wherein channels selected as recommended channels are located may be displayed. A user may select a recommended channel by moving the cursor to the location wherein the indicator is located.
  • a recommended broadcast channel may be displayed differently from other broadcast channels on an EPG (e.g., displayed in a different color).
  • a UI element which enables selection of music selected as recommended music may be displayed. A user may select desired music through the UI element and play the music.
  • a content to be recommended is an application
  • a specific event e.g., if a preset time comes
  • a UI element including an icon corresponding to an application selected as a recommended application may be displayed.
  • a user may select a desired application through the UI element and execute the application. If ‘SEE MORE’ is selected, applications in the next ranks, i.e., applications of which use indices are the next biggest may be displayed.
  • recommendation information is provided at the electronic device 100 , but it is also possible that recommendation information is provided at an external device of the electronic device 100 .
  • the electronic device 100 may provide information on a recommended content to a large screen device such as a TV through wireless communication such as mirroring, DLNA, and Wi-Fi, and thus information on a recommended content may be displayed on a large screen.
  • a recommended content which is adaptive according to a content use pattern of each user may be provided. Specifically, by determining weights W 1 , W 2 , W 3 added to a history adaptively according to a content use pattern of a user, a content which is more appropriate for a user's tendency may be recommended. For this, according to an embodiment of the disclosure, a content use pattern index which digitized a user's content use pattern may be used.
  • a content use pattern index is, for example, digitation of a user's content use pattern such as a user's content use pattern of mainly using contents only in a specific time, a user's content use pattern of mainly using contents only on a specific day, and a user's content use pattern of evenly using contents in all times.
  • the processor 120 may calculate a use pattern index of a content based on history information stored in the memory 110 .
  • a content use pattern index may be set such that the content use pattern index becomes bigger as the degree of being distanced from the average becomes bigger by introducing the concept of dispersion. Accordingly, a user's content use pattern index wherein a content use ratio of a specific day or a specific time is big is bigger than a user's content use pattern index wherein contents are evenly used in all times or on all days.
  • a content use pattern index may include at least one of a day pattern index or a time pattern index.
  • a day pattern index may be calculated based on use history for each day, and a time pattern index may be calculated based on use history for each time.
  • the processor 120 may calculate dispersion for use times for each day with respect to each of a plurality of contents based on history information stored in the memory 110 , and calculate a day pattern index based on the calculated dispersion. For example, in case first to third contents were used according to history information, the processor 120 may calculate dispersion for use times for each day with respect to the first content, calculate dispersion for use times for each day with respect to the second content, and calculate dispersion for use times for each day with respect to the third content. The sum of multiplications of the use ratios of contents with respect to the first to third contents with each calculated dispersion becomes a day pattern index.
  • the processor 120 may calculate dispersion for use times for each time with respect to each of a plurality of contents based on history information stored in the memory 110 , and calculate a time pattern index based on the calculated dispersion. For example, in case first to third contents were used according to history information, the processor 120 may calculate dispersion for use times for each time with respect to the first content, calculate dispersion for use times for each time with respect to the second content, and calculate dispersion for use times for each time with respect to the third content. The sum of multiplications of the use ratios of contents with respect to the first to third contents with each calculated dispersion becomes a time pattern index.
  • a use history which becomes a basis for calculating a content use pattern index may be, for example, a use history of a recent few weeks or days, or the entire use history.
  • a history of use shorter than a predetermined time period e.g., ten minutes
  • the processor 120 may determine weights based on content use pattern indices for a plurality of contents. For example, information on different weights for each content use pattern index may be stored in advance in the memory 110 , and the processor 120 may select a weight corresponding to the currently calculated content use pattern index from the pre-stored information on weights.
  • a content use pattern index is calculated based on history information, if history information is updated according to use of the electronic device 100 , a content use pattern index is re-calculated based on the updated history information, and a weight is also updated based on the re-calculated content use pattern index. Update may be performed for every predetermined period.
  • a weight adaptively changes according to change of a viewing history and thus a content that suits a user's recent content use pattern can be recommended. Also, there is an advantage that recommendation can be performed in real time on the electronic device 100 (on-device real—time), but not based on a server.
  • a weight that suits the characteristic may be determined. For this, by clustering content use pattern indices calculated from the electronic device 100 as described above and content use pattern indices calculated at other electronic devices, a weight corresponding to the cluster to which the content use pattern indices calculated at the electronic device 100 belong may be selected. An operation of clustering content use pattern indices may be performed at an external server.
  • the electronic device 100 and other electronic devices may transmit content use pattern indices to a server, and the server may apply an artificial intelligence technology to collected data and figure out which characteristic a user's content use pattern of each electronic device has.
  • the server may apply an artificial intelligence technology to collected data and figure out which characteristic a user's content use pattern of each electronic device has.
  • other electronic devices are devices having high relevance to the electronic device. This is because it can be advantageous to compare users' content use patterns of devices having relevance to one another in deriving a meaningful result.
  • other electronic devices may be within the same area as the electronic device.
  • the electronic device and other electronic devices may be TVs used in homes in a specific city.
  • An artificial intelligence technology consists of a machine learning (deep learning) technology using an algorithm which classifies/learns the characteristics of input data by itself, and element technologies of simulating functions of a human brain such as cognition and determination by using a machine learning algorithm.
  • the server may cluster content use patterns of each electronic device.
  • Knowledge representation is a technology of automatically processing information of human experiences into knowledge data, and includes knowledge construction (data generation/classification), knowledge management (data utilization), and the like.
  • the server may cluster content use pattern indices based on a value of standard deviation 6 of collected content use pattern indices into bundles in an N number, and classify them.
  • the server may classify collected time pattern indices into a cluster of weak time patterns (a time pattern index ⁇ 0.5 ⁇ ), a cluster of intermediate time patterns (0.5 ⁇ a time pattern index ⁇ ), and a cluster of strong time patterns (a time pattern index> ⁇ ).
  • the server may classify collected day pattern indices into a cluster of weak day patterns (a day pattern index ⁇ 0.5 ⁇ ), a cluster of intermediate day patterns (0.5 ⁇ a day pattern index ⁇ ), and a cluster of strong day patterns (a day pattern index> ⁇ ).
  • nine groups may be defined.
  • the first weight W 1 , the second weight W 2 , and the third weight W 3 may be set to suit the characteristics of each of the nine groups.
  • a weight is set such that a stronger pattern has a bigger value.
  • a time weight is set to be high
  • a day weight is set to be high.
  • the server transmits information on weights corresponding to groups to which each of the electronic device 100 and other electronic devices belongs to the electronic device 100 .
  • a model selecting a recommended content based on history information and weights may be implemented in the electronic device 100 , and the server may derive a parameter for grouping by utilizing a large amount of data and the model of the electronic device 100 may be updated based on this value. Accordingly, a recommended content may be selected by reflecting a content use pattern that can continuously change with utilization of minimum resources.
  • the electronic device 100 may receive information on content use pattern indices from other electronic devices and perform clustering as in the aforementioned method, and a weight may be determined based on information on a weight corresponding to the cluster to which the electronic device 100 belongs.
  • the operations performed at the electronic device 100 are performed at the server.
  • the electronic device 100 provides history information to the server, and the server calculates a content use pattern index.
  • the server calculates a use index and selects a recommended content and provides information in this regard to the electronic device 100 . That is, it is possible that main operations are made to be performed at the server, and the electronic device 100 is made to just take charge of an outputting function of information.
  • history information is personal information, it is preferable that the information is not leaked to the outside.
  • a method wherein the electronic device 100 transmits a content use pattern index acquired by processing history information to the server, instead of history information may be preferred.
  • a recommended content which has high possibility of being used may be provided not based on history information stored in the electronic device 100 , but based on history information of other electronic devices.
  • a server may receive history information from at least one of other electronic devices, and calculate a content use pattern index and a content use index as described above based on the received history information and select a recommended content, and provide information on the selected recommended content to the electronic device.
  • the electronic device 100 may directly receive history information from at least one of other electronic devices not via the server, and calculate a content use pattern index and a content use index as described above based on the received history information and select a recommended content.
  • a content that a user of another electronic device prefers may be provided at the electronic device 100 .
  • FIG. 6 is a diagram for illustrating a method for calculating a recommendation hit ratio based on a recommended content.
  • the processor 120 may increase the count values for the channel as much as +1. For example, if a user selected channel number 5 in a list of recommended contents as in FIG. 6 , the processor 120 may add a value of +1 regarding the channel number 5 . Also, the processor 120 may compare count values like (1/0/0/0/0/0). In this regard, if the user views channel number 5 again at the same time the next week, the processor 120 may increase the count values like (2/0/0/0/0). Meanwhile, if the user views channel number 3 at the same time the next week, the processor 120 may increase the count values like (2/1/0/0/0/0).
  • the order of channels may be changed according to the use ratio of a recommended content or a recommendation hit ratio, although the channels are displayed in an arrangement for promoting understanding.
  • the number by which the count values increase may be another number which is not 1, and the method may be a different method other than an addition method.
  • a recommendation hit ratio may be calculated in consideration of selection frequency. For example, in the case of (2/1/0/0/0/0), channel number 5 may be calculated as a recommendation hit ratio of 66%.
  • the calculated recommendation hit ratios for each channel may be stored in the memory 110 . In this case, recommendation hit ratios may be calculated for each channel and the recommendation hit ratios may be divided in more detail in consideration of days and times, and stored in the memory 110 .
  • a use index may be considered, or a use index and a recommendation hit ratio may be applied simultaneously.
  • FIGS. 7 to 9 are flow charts for illustrating a method for recommending a content according to an embodiment of the disclosure.
  • FIG. 7 is a diagram for illustrating a method for recommending a content in case the power of a display is turned off and is then turned on.
  • viewing history information on a content that a user views may be collected at operation S 710 . If a user was viewing channel number 7 when turning off the display 131 of the power device at operation S 720 , information on the recent viewing history may be stored in the memory 110 . Afterwards, if the user turns on the display 131 of the power device at operation S 730 , it is general that the channel number 7 is displayed. However, by using the day and the time when the display 131 of the power device was turned on, previous user history information may be collected and a recommended content may be provided at operation S 740 . A method for providing a recommended content may be displaying a list of a plurality of contents or moving directly to a channel corresponding to the recommended content.
  • use indices may be calculated for each selected recommended content in the list by using previous user history information.
  • control may be performed such that the channel number 11 is displayed immediately when a user turns on the display 131 .
  • an operation of turning on or off the display may mean that a user changes the mode of the electronic device 100 from a power saving mode to a normal mode or from a normal mode to a power saving mode.
  • a power saving mode may mean a state wherein the electronic device is connected to a consent but an image is not displayed on the display panel.
  • a channel of which use index is the highest may be displayed immediately, but a recommendation hit ratio may be additionally calculated and control may be performed such that channel number 11 is displayed only when the recommendation hit ratio is greater than or equal to a threshold value, and if the recommendation hit ratio is smaller than a threshold value, control may be performed such that channel number 7 that a user was recently viewing when the display 131 of the electronic device 100 was turned off is displayed.
  • the number of times of changing channels by a user may be determined as one of specific events. Setting may be made such that, if the number of times of changing channels by a user during a specific time period is greater than or equal to a predetermined number of times of changing channels, it falls under a specific event. For example, a user may store a threshold number of times as ten in the memory 110 , etc. in advance. In this case, if the number of times that the user changed channels during a specific time period becomes ten, a recommended content may be displayed to the user.
  • Displaying a recommended content may mean displaying a UI element inquiring to the user whether to select a recommended content, and in case there are a plurality of recommended contents, it may mean displaying a list and displaying a UI element such as a menu.
  • FIG. 7 an operation wherein a user turns on the display at operation S 730 is described, but this may merely be one operation among specific events.
  • FIG. 8 an operation in case the number of times of changing channels is greater than a threshold number of times which is another embodiment of a specific event will be described.
  • FIG. 8 is a flow chart for illustrating a method for recommending a content in consideration of a specific behavior of a user.
  • a user's number of times of changing channels it may be determined whether a user's number of times of changing channels is greater than a threshold number of times at operation S 810 .
  • a recommended content may be displayed at operation S 820 .
  • the electronic device may not operate until another specific event occurs.
  • FIG. 9 is a flow chart for illustrating a method for recommending a content in consideration of a recommendation hit ratio and whether a user cancels a recommendation function.
  • history information of a user may be collected and stored in the memory 110 , etc. at operation S 910 . Then, when the user turns on the display 131 at operation S 920 , it may be recognized as one of specific events, and contents for the date and the time may be selected. Also, use indices and recommendation hit ratios of each content recommended on the date and the time among a plurality of selected contents may be calculated.
  • control may be performed such that, in case a recommendation hit ratio of a content among a plurality of contents is higher than a threshold value, the channel may be moved directly to that recommended content at operation S 940 , and in case a recommendation hit ratio of a content is lower than a threshold value, the electronic device may wait until the next specific event occurs.
  • a specific event occurs at operation S 950 , it may be determined whether the number of times that a user of the recommended content is greater than or equal to a threshold number of times at operation S 960 .
  • the number of times of cancellation means that, even though the electronic device 100 provided a recommended content for the user's convenience, but the user did not accept it and did not select the recommended content, and also, it may mean that the user cancels provision of the recommended content.
  • a recommendation function may not be provided, and in case a user cancelled a recommendation function smaller than a threshold number of times or a user did not cancel a recommendation function, the recommended content may be displayed at operation S 970 .
  • displaying the recommended content may mean displaying a UI element inquiring to the user whether to select the recommended content, and in case there are a plurality of recommended contents, it may mean displaying a list and displaying a UI element such as a menu.
  • FIG. 10 is a flow chart for illustrating a method for recommending a content according to another embodiment of the disclosure.
  • the server may store viewing history information of a user at operation S 1010 .
  • the electronic device 100 may transmit the fact that a specific event occurred to the server at operation S 1020 .
  • the server may recommend a content corresponding to the time point when the specific event occurred by using the viewing history information of the user at operation S 1030 .
  • the meaning of recommendation does not mean an active operation of displaying a content on the display 131 for a user, but may mean an operation of making a list of contents for recommending a content to a user.
  • the server may calculate the recommendation hit ratio of the recommended content at operation S 1040 . Afterwards, in case the recommendation hit ratio is higher than a threshold value, the recommended content may be transmitted to the electronic device 100 at operation S 1050 . In this case, the electronic device 100 may receive the recommended content transmitted from the server and display the content on the display 131 .
  • displaying the recommended content may mean displaying a UI element inquiring to the user whether to select the recommended content, and in case there are a plurality of recommended contents, it may mean displaying a list and displaying a UI element such as a menu.
  • FIG. 11 is a flow chart for illustrating a method for recommending a content by the electronic device 100 according to an embodiment of the disclosure.
  • the step of recommending a content based on a viewing history S 1110 and the step of calculating recommendation hit ratios for each day and time according to the selection frequency of the recommended content S 1120 and storing the recommendation hit ratios may be included.
  • a method for recommending a content by the electronic device 100 may include the step of, based on a specific event occurring, comparing a recommendation hit ratio corresponding to the day and the time when the specific event occurred and a threshold value S 1130 .
  • the specific event may be an event wherein the number of times of changing broadcast channels during a predetermined time period exceeds a threshold number of times, or an event wherein a tuned state of a broadcast channel is maintained exceeding a predetermined time period, or an event wherein a viewing starting time or a viewing finishing time predicted on the basis of the viewing history comes.
  • the step of recommending a content based on a viewing history may include the steps of applying a first weight to the day of viewing a content provided at the electronic device 100 earlier, and applying a second weight to the time of viewing and recommending a content based on a result of combination of the first weight and the second weight.
  • the method for recommending a content by the electronic device 100 may include the step of, based on a recommendation hit ratio being higher than a threshold value, directly displaying a content of which recommendation hit ratio is the maximum among contents recommended when the event occurred, and based on a recommendation hit ratio being lower than a threshold value, providing a menu which enables selection of a content recommended when the event occurred S 1140 .
  • the method for recommending a content by the electronic device 100 may include the steps of, based on cancellation of a menu being repeated greater than or equal to a threshold number of times, inactivating a content recommendation function, and based on viewing of the content of which recommendation hit ratio is the maximum being cancelled greater than or equal to a threshold number of times, inactivating a content recommendation function.
  • a weight may be added according to a day and a time in a viewing history and a history index may be calculated, or a recommendation hit ratio may be additionally calculated. Determination according to a day and a time is based on the feature that a user's content consumption pattern is repeated by a unit of a week, and this may be one month or one day, but not one week, according to a user's habit. If different weights are added according to days and times, a content that a user consumes on a specific day at a specific time can be analyzed precisely, and weights may be adjusted appropriately for a user. Also, if a reduction value is used, a content can be recommended mainly based on contents that a user recently consumed, and thus a user's changing consumption pattern can be reflected.
  • a recommended content is appropriate for a user, and values that a user can set in advance such as a weight and a threshold value may be changed by reflecting this.
  • values that a user can set in advance such as a weight and a threshold value may be changed by reflecting this.
  • a weight and a threshold value may be changed by reflecting this.
  • a content that is more appropriate for a user can be recommended.
  • a user's pattern that did not use a recommendation function may be analyzed. By reflecting a user's intention by counting the number of times of not using a recommendation function, a consumer's satisfaction can be heightened.
  • an operation of converting (displaying) a content directly under a specific condition, etc. may be performed, and thus a user can access a content that he wishes to view easily, without a separate access to a menu.
  • the aforementioned method for recommending a content by the electronic device 100 may be implemented as at least one execution program for executing the aforementioned control method, and such an execution program may be stored in a non-transitory readable medium.
  • a non-transitory readable medium means a medium that stores data semi-permanently, and is readable by machines, but not a medium that stores data for a short moment such as a register, a cache, and a memory.
  • the aforementioned various applications or programs may be provided while being stored in a non-transitory readable medium such as a CD, a DVD, a hard disk, a blue-ray disk, a USB, a memory card, a ROM and the like.
  • a non-transitory readable medium means a medium that stores data semi-permanently, and is readable by machines, but not a medium that stores data for a short moment such as a register, a cache, and a memory.
  • the aforementioned programs may be provided while being stored in a non-transitory readable medium such as a CD, a DVD, a hard disk, a blue-ray disk, a USB, a memory card, a ROM and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Social Psychology (AREA)
  • Human Computer Interaction (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Software Systems (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
US16/638,354 2017-09-26 2018-09-21 Electronic device and control method therefor Active US11064261B2 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
KR1020170124400A KR102395243B1 (ko) 2017-09-26 2017-09-26 전자 장치 및 이의 제어방법
KR10-2017-0124400 2017-09-26
PCT/KR2018/011314 WO2019066432A1 (fr) 2017-09-26 2018-09-21 Dispositif électronique et son procédé de commande

Publications (2)

Publication Number Publication Date
US20200169789A1 US20200169789A1 (en) 2020-05-28
US11064261B2 true US11064261B2 (en) 2021-07-13

Family

ID=65903035

Family Applications (1)

Application Number Title Priority Date Filing Date
US16/638,354 Active US11064261B2 (en) 2017-09-26 2018-09-21 Electronic device and control method therefor

Country Status (4)

Country Link
US (1) US11064261B2 (fr)
EP (1) EP3641323B1 (fr)
KR (1) KR102395243B1 (fr)
WO (1) WO2019066432A1 (fr)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019106867A1 (fr) * 2017-11-30 2019-06-06 パナソニックＩｐマネジメント株式会社 Dispositif de délivrance d'image, procédé de commande de dispositif de délivrance d'image, et télévision
CN110413169B (zh) * 2019-07-24 2021-11-23 北京小米移动软件有限公司 一种信息展示方法、装置及介质
KR102708367B1 (ko) * 2019-08-26 2024-09-20 엘지전자 주식회사 선호도 기반 서비스 제공 시스템, 장치 및 방법
KR102820093B1 (ko) * 2019-11-15 2025-06-13 에스케이텔레콤 주식회사 딥러닝 기반의 상황인지 컨텐츠 추천을 위한 장치 및 이를 위한 방법
KR102250135B1 (ko) * 2020-05-29 2021-05-10 박준영 추천 동영상 제공 방법 및 이를 위한 장치
KR102860668B1 (ko) * 2020-10-08 2025-09-15 에스케이텔레콤 주식회사 사용자에게 컨텐츠 추천 메뉴를 제공하는 방법 및 상기 방법을 수행하는 컨텐츠 추천 장치
CN112380592B (zh) * 2020-10-28 2024-04-12 中车工业研究院有限公司 设计推荐系统及方法、电子设备及可读存储介质
US11509965B2 (en) * 2020-11-06 2022-11-22 Rovi Guides, Inc. Systems and methods for providing content recommendations
KR20240038992A (ko) * 2021-10-28 2024-03-26 엘지전자 주식회사 Tv 및 그 제어 방법
CN114554278B (zh) * 2022-01-28 2023-12-19 青岛海尔科技有限公司 播放控制方法及装置、存储介质及电子装置
US12162507B2 (en) * 2022-03-07 2024-12-10 Toyota Research Institute, Inc. Vehicle-provided recommendations for use of ADAS systems
CN114780842B (zh) * 2022-04-20 2022-12-13 北京字跳网络技术有限公司 一种数据处理方法、装置、设备及存储介质
KR20250006636A (ko) * 2023-07-04 2025-01-13 삼성전자주식회사 전자 장치 및 그 제어 방법
KR102692909B1 (ko) * 2023-08-18 2024-08-08 쿠팡 주식회사 콘텐츠 스트리밍 서비스에서 정보를 제공하는 전자 장치 및 이를 위한 방법

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20000051975A (ko) 1999-01-28 2000-08-16 구자홍 티브이(ｔｖ) 방송 채널간의 선호 채널 표시방법
US20040003395A1 (en) * 2002-06-28 2004-01-01 Gutta Srinivas Automatic display of a recommended program onto PIP display
US20070146331A1 (en) 2005-12-28 2007-06-28 Samsung Electronics Co., Ltd. Remote controller and display system
KR20080029088A (ko) 2006-09-28 2008-04-03 엘지전자 주식회사 티브이 및 이를 이용한 선호 채널 제공 방법
KR20080058637A (ko) 2006-12-22 2008-06-26 주식회사 알티캐스트 추천 컨텐츠 제공 시스템 및 그 방법
JP2008193431A (ja) 2007-02-05 2008-08-21 Fujitsu Ltd コンテンツ推薦装置、コンテンツ推薦方法、およびコンテンツ推薦プログラム
US20100251305A1 (en) * 2009-03-30 2010-09-30 Dave Kimble Recommendation engine apparatus and methods
JP2011146766A (ja) 2010-01-12 2011-07-28 Panasonic Corp 放送波受信装置および放送波受信装置における画面表示制御方法
US8024756B2 (en) 2008-04-10 2011-09-20 Sony Corporation TV user interface for viewing selected sub-groups of channels
JP2012023636A (ja) 2010-07-15 2012-02-02 Nippon Hoso Kyokai <Nhk> コンテンツ提示装置及びコンテンツ提示プログラム
US20120151511A1 (en) 2010-12-09 2012-06-14 Samsung Electronics Co., Ltd. Multimedia system and method of recommending multimedia content
US20140337412A1 (en) 2013-05-08 2014-11-13 Samsung Electronics Co., Ltd. Content providing method and device
KR20150042584A (ko) 2013-10-11 2015-04-21 삼성전자주식회사 컨텐츠 추천을 위한 컨텐츠 제공 장치, 시스템 및 방법
EP3041250A1 (fr) 2013-08-30 2016-07-06 LG Electronics Inc. Appareil d'affichage d'image et procédé de fonctionnement associé
US20160274744A1 (en) * 2015-03-17 2016-09-22 Comcast Cable Communications, Llc Real-Time Recommendations and Personalization
JP2017167906A (ja) 2016-03-17 2017-09-21 Kddi株式会社 番組推薦装置、番組推薦方法及び番組推薦プログラム

Patent Citations (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20000051975A (ko) 1999-01-28 2000-08-16 구자홍 티브이(ｔｖ) 방송 채널간의 선호 채널 표시방법
US20040003395A1 (en) * 2002-06-28 2004-01-01 Gutta Srinivas Automatic display of a recommended program onto PIP display
US20070146331A1 (en) 2005-12-28 2007-06-28 Samsung Electronics Co., Ltd. Remote controller and display system
KR20070069613A (ko) 2005-12-28 2007-07-03 삼성전자주식회사 리모콘 및 이를 포함하는 디스플레이 시스템
US9143717B2 (en) 2006-09-28 2015-09-22 Lg Electronics Inc. Broadcast receiver and method of providing preferred channel thereof
KR20080029088A (ko) 2006-09-28 2008-04-03 엘지전자 주식회사 티브이 및 이를 이용한 선호 채널 제공 방법
KR20080058637A (ko) 2006-12-22 2008-06-26 주식회사 알티캐스트 추천 컨텐츠 제공 시스템 및 그 방법
JP2008193431A (ja) 2007-02-05 2008-08-21 Fujitsu Ltd コンテンツ推薦装置、コンテンツ推薦方法、およびコンテンツ推薦プログラム
US8024756B2 (en) 2008-04-10 2011-09-20 Sony Corporation TV user interface for viewing selected sub-groups of channels
US20100251305A1 (en) * 2009-03-30 2010-09-30 Dave Kimble Recommendation engine apparatus and methods
JP2011146766A (ja) 2010-01-12 2011-07-28 Panasonic Corp 放送波受信装置および放送波受信装置における画面表示制御方法
JP2012023636A (ja) 2010-07-15 2012-02-02 Nippon Hoso Kyokai <Nhk> コンテンツ提示装置及びコンテンツ提示プログラム
KR20120064612A (ko) 2010-12-09 2012-06-19 삼성전자주식회사 멀티미디어 시스템 및 멀티미디어 컨텐츠 추천 방법
US20120151511A1 (en) 2010-12-09 2012-06-14 Samsung Electronics Co., Ltd. Multimedia system and method of recommending multimedia content
US20140337412A1 (en) 2013-05-08 2014-11-13 Samsung Electronics Co., Ltd. Content providing method and device
KR20140132658A (ko) 2013-05-08 2014-11-18 삼성전자주식회사 콘텐트 제공 방법, 콘텐트 제공 장치 및 그 콘텐트 제공 시스템
US10123064B2 (en) 2013-05-08 2018-11-06 Samsung Electronics Co., Ltd. Content providing method and device
EP3041250A1 (fr) 2013-08-30 2016-07-06 LG Electronics Inc. Appareil d'affichage d'image et procédé de fonctionnement associé
KR20150042584A (ko) 2013-10-11 2015-04-21 삼성전자주식회사 컨텐츠 추천을 위한 컨텐츠 제공 장치, 시스템 및 방법
US10097895B2 (en) 2013-10-11 2018-10-09 Samsung Electronics Co., Ltd Content providing apparatus, system, and method for recommending contents
US20160274744A1 (en) * 2015-03-17 2016-09-22 Comcast Cable Communications, Llc Real-Time Recommendations and Personalization
JP2017167906A (ja) 2016-03-17 2017-09-21 Kddi株式会社 番組推薦装置、番組推薦方法及び番組推薦プログラム

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Extended European Search Report dated Sep. 30, 2020 from European Application No. 18862844.0, 6 pages.
International Search Report dated Jan. 18, 2019 from International Patent Application No. PCT/KR2018/011314.
Written Opinion of the International Searching Authority dated Jan. 18, 2019 from International Patent Application No. PCT/KR2018/011314, 13 pages.

Also Published As

Publication number Publication date
EP3641323B1 (fr) 2024-10-30
EP3641323A1 (fr) 2020-04-22
KR20190035324A (ko) 2019-04-03
KR102395243B1 (ko) 2022-05-06
WO2019066432A1 (fr) 2019-04-04
EP3641323A4 (fr) 2020-10-28
US20200169789A1 (en) 2020-05-28

Similar Documents

Publication Publication Date Title
US11064261B2 (en) Electronic device and control method therefor
KR102384215B1 (ko) 전자 장치 및 그의 제어방법
US20220337915A1 (en) Methods, systems, and media for presenting suggestions of media content
US11412308B2 (en) Method for providing recommended channel list, and display device according thereto
US10067934B1 (en) Method and system for generating dynamic text responses for display after a search
US20150334461A1 (en) Methods and systems for dynamically recommending favorite channels or programs
US10298978B2 (en) Interest prediction
KR102611422B1 (ko) 디스플레이 장치 및 그 컨텐츠 추천 방법
US20200221179A1 (en) Method of providing recommendation list and display device using the same
CN113302946B (zh) 电子装置及其控制方法
KR102384209B1 (ko) 전자 장치 및 이의 제어 방법
US20170280197A1 (en) Information recommend system, information recommend method and non-transitory computer-readable storage medium
US20260093504A1 (en) Systems and methods for using ai to populate a customized start up menu out of standby
CN109275023A (zh) 电视频道排序方法、电视及存储介质

Legal Events

Date Code Title Description
AS Assignment

Owner name: SAMSUNG ELECTRONICS CO., LTD., KOREA, REPUBLIC OF

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:KIM, DO-SUNG;KIM, SUNG-WON;BAE, MU-GONG;AND OTHERS;REEL/FRAME:051786/0817

Effective date: 20200117

FEPP Fee payment procedure

Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

STPP Information on status: patent application and granting procedure in general

Free format text: NON FINAL ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER

STPP Information on status: patent application and granting procedure in general

Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS

STPP Information on status: patent application and granting procedure in general

Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT RECEIVED

STPP Information on status: patent application and granting procedure in general

Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED

STCF Information on status: patent grant

Free format text: PATENTED CASE

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 4